© 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. 29631
    Prev
    Next
    INDEX
    Explanations

    prepositions and function words

    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
     surfaced
    -0.09
    ರ್ಗ
    -0.08
     Ying
    -0.08
     გამო�
    -0.07
     paralle
    -0.07
     seld
    -0.07
    .api
    -0.07
     xid
    -0.07
     પાણી
    -0.07
     streams
    -0.07
    POSITIVE LOGITS
    iberal
    0.08
     בכלל
    0.08
    Articles
    0.08
     ب
    0.07
    ilter
    0.07
    uman
    0.07
    utm
    0.07
    なら
    0.07
    rier
    0.07
    -answer
    0.07
    Activations Density 0.217%

    No Known Activations