© 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. 108706
    Prev
    Next
    INDEX
    Explanations

    <|channel|>

    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
     Mok
    -0.08
     ((*
    -0.08
     거리
    -0.08
     afar
    -0.08
    順位
    -0.07
    orsch
    -0.07
     दूरी
    -0.07
    روق
    -0.07
     Louvre
    -0.07
    ormon
    -0.07
    POSITIVE LOGITS
     teen
    0.09
     emojis
    0.09
    trade
    0.08
    एम
    0.08
    _v
    0.07
     emoji
    0.07
    Response
    0.07
    uppercase
    0.07
     braided
    0.07
     risposta
    0.07
    Activations Density 0.030%

    No Known Activations