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. 77522
    Prev
    Next
    INDEX
    Explanations

    collective nouns

    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
    ñez
    -0.08
     לחל
    -0.08
    网址
    -0.08
    irt
    -0.08
     Juventus
    -0.08
    .jsp
    -0.08
    irio
    -0.08
    itir
    -0.07
     virtue
    -0.07
    amilton
    -0.07
    POSITIVE LOGITS
     flock
    0.09
     handful
    0.09
     واحد
    0.08
    verband
    0.08
    Piece
    0.08
    -piece
    0.08
     doses
    0.08
    ご
    0.08
     объ
    0.08
     thousand
    0.08
    Activations Density 0.046%

    No Known Activations