© 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. 11-RESID-POST-AA
    11. 110765
    Prev
    Next
    INDEX
    Explanations

    types of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rain
    -0.09
    pois
    -0.08
     pantal
    -0.08
    aisseur
    -0.08
    astanza
    -0.08
     Rain
    -0.08
     rain
    -0.08
     distortion
    -0.08
    환
    -0.08
     पंज
    -0.07
    POSITIVE LOGITS
     отно
    0.08
     cop
    0.08
     решений
    0.08
     które
    0.07
    idel
    0.07
    -fl
    0.07
     Malt
    0.07
     другого
    0.07
     которых
    0.07
    ,s
    0.07
    Activations Density 0.212%

    No Known Activations