© 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. 43
    Prev
    Next
    INDEX
    Explanations

    end

    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
     fools
    -0.08
     реал
    -0.07
     scrutin
    -0.07
    elu
    -0.07
    542
    -0.07
    tte
    -0.07
    /forms
    -0.07
    ('../
    -0.07
     ciment
    -0.07
     подготов
    -0.07
    POSITIVE LOGITS
     Inclusive
    0.11
     inclusive
    0.11
    Inclusive
    0.10
     angegeben
    0.10
     Inclus
    0.09
    inclusive
    0.09
    ेंज
    0.09
     endpoints
    0.09
     �
    0.09
    Inclus
    0.08
    Activations Density 0.045%

    No Known Activations