© 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. 48019
    Prev
    Next
    INDEX
    Explanations

    x

    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
     Mys
    -0.08
     mashed
    -0.08
    .Gu
    -0.07
     firm
    -0.07
    ږ
    -0.07
    унок
    -0.07
     тор
    -0.07
    /write
    -0.07
     umuk
    -0.07
     kok
    -0.07
    POSITIVE LOGITS
    [::-
    0.08
    ","+
    0.08
     hinweg
    0.07
    490
    0.07
    pole
    0.07
    BZ
    0.07
    610
    0.07
     השני
    0.07
     convenient
    0.07
    LI
    0.07
    Activations Density 0.018%

    No Known Activations