© 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. 51663
    Prev
    Next
    INDEX
    Explanations

    ph

    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
     Schwar
    -0.08
     exchanged
    -0.08
     Impression
    -0.08
     electro
    -0.08
    umwa
    -0.07
     Crosby
    -0.07
    UA
    -0.07
    uario
    -0.07
    bate
    -0.07
    ermo
    -0.07
    POSITIVE LOGITS
    ases
    0.17
    ased
    0.16
    asing
    0.15
    asis
    0.12
    asen
    0.12
     fases
    0.11
     مراحل
    0.10
     phases
    0.10
    asal
    0.10
    asic
    0.09
    Activations Density 0.001%

    No Known Activations