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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95264
    Prev
    Next
    INDEX
    Explanations

    Les Misérables

    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
     영상
    -0.08
     muebles
    -0.08
    영상
    -0.08
     فيديو
    -0.08
     ffi
    -0.08
     DEFIN
    -0.08
     {:?
    -0.08
    动漫
    -0.08
     videoer
    -0.08
    anos
    -0.08
    POSITIVE LOGITS
     homelessness
    0.09
     clock
    0.09
    -clock
    0.08
    866
    0.07
     conceal
    0.07
    .clock
    0.07
     protections
    0.07
    clock
    0.07
     permit
    0.07
    _CLOCK
    0.07
    Activations Density 0.004%

    No Known Activations