Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 105966
    Prev
    Next
    INDEX
    Explanations

    var and numbers

    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
    ിയെ
    -0.09
     Ndị
    -0.09
     Anyị
    -0.09
     célib
    -0.09
    ി
    -0.08
    iltä
    -0.08
    െയുള്ള
    -0.08
     nyocha
    -0.08
     ọtụtụ
    -0.08
     Bachelor
    -0.08
    POSITIVE LOGITS
     guarded
    0.08
     interplay
    0.07
    ength
    0.07
    Taken
    0.07
    amarin
    0.07
     mods
    0.07
     tandem
    0.07
    angered
    0.07
     lieber
    0.07
     solicitudes
    0.07
    Activations Density 0.000%

    No Known Activations