© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47961
    Prev
    Next
    INDEX
    Explanations

    Numbers and free items

    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
     മന്ത്ര
    -0.09
     அமைச்ச
    -0.09
     ಸಚಿವ
    -0.09
     υπουργ
    -0.08
     અથ
    -0.08
    ниқ
    -0.08
     sprites
    -0.08
     razgov
    -0.08
    caler
    -0.08
     ಸಚ
    -0.08
    POSITIVE LOGITS
     .*
    0.08
     <?=
    0.08
    .*?)
    0.07
    <?=
    0.07
    ició
    0.07
    Gracias
    0.07
     thanks
    0.07
    .Language
    0.07
    确保
    0.07
     fish
    0.07
    Activations Density 0.333%

    No Known Activations