© 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. 108626
    Prev
    Next
    INDEX
    Explanations

    compress

    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
    Pole
    -0.08
    pu
    -0.08
    幼
    -0.08
    389
    -0.08
     pupil
    -0.08
     Pole
    -0.07
    Prote
    -0.07
     kindergarten
    -0.07
    #$
    -0.07
    Touched
    -0.07
    POSITIVE LOGITS
    ification
    0.09
     seques
    0.08
    ierung
    0.08
    城
    0.08
     methane
    0.07
    Duff
    0.07
    さ
    0.07
    ible
    0.07
     Lisa
    0.07
    ify
    0.07
    Activations Density 0.007%

    No Known Activations