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. 12302
    Prev
    Next
    INDEX
    Explanations

    tax

    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
    typen
    -0.08
    .cc
    -0.08
    姓名
    -0.08
     uitstraling
    -0.07
    ïde
    -0.07
     cyclists
    -0.07
     RSV
    -0.07
    énd
    -0.07
     Vote
    -0.07
     siguiendo
    -0.07
    POSITIVE LOGITS
     Boutique
    0.07
     avantaj
    0.07
     negativa
    0.07
     minim
    0.07
    -friendly
    0.07
     бонус
    0.07
     bort
    0.07
     birlik
    0.07
     praz
    0.07
     penal
    0.07
    Activations Density 0.008%

    No Known Activations