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. 23154
    Prev
    Next
    INDEX
    Explanations

    Code/HTML snippets

    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
    <|endoftext|>
    -0.09
    <|reserved_200016|>
    -0.08
    (buff
    -0.08
     ner
    -0.08
    adem
    -0.07
    Rot
    -0.07
    ugn
    -0.07
     sgr
    -0.07
    /grid
    -0.07
     серв
    -0.07
    POSITIVE LOGITS
     Review
    0.07
    ковых
    0.07
     Reviewer
    0.07
     précédente
    0.07
     Stanton
    0.07
     erfolgreichen
    0.07
      ↵  ↵
    0.07
     theolog
    0.07
     комплек
    0.07
     Letter
    0.07
    Activations Density 0.140%

    No Known Activations