Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9274
    Prev
    Next
    INDEX
    Explanations

    honey

    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
     boc
    -0.08
     schauen
    -0.08
     pendientes
    -0.08
     kijken
    -0.08
     FS
    -0.08
    илгын
    -0.08
     Leasing
    -0.07
    UGH
    -0.07
     pendiente
    -0.07
     aast
    -0.07
    POSITIVE LOGITS
     Magnum
    0.09
    とは
    0.08
     flowing
    0.08
    �
    0.07
     syrup
    0.07
    .loads
    0.07
    apia
    0.07
     apocalypse
    0.07
     syr
    0.07
    媒
    0.07
    Activations Density 0.003%

    No Known Activations