© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51647
    Prev
    Next
    INDEX
    Explanations

    Aud

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophagus
    -0.08
     selvfølgelig
    -0.07
     blister
    -0.07
    审
    -0.07
    ////////////////////////////////////////////////////////////////////////////
    -0.07
    	sub
    -0.07
     dept
    -0.07
    GS
    -0.07
     ostream
    -0.07
    athan
    -0.07
    POSITIVE LOGITS
     possibilità
    0.08
     possibility
    0.08
     fre
    0.08
     int
    0.08
     Möglichkeit
    0.08
     birds
    0.07
    ungsver
    0.07
     funcionalidades
    0.07
     posibilidad
    0.07
    ciones
    0.07
    Activations Density 0.000%

    No Known Activations