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. 45117
    Prev
    Next
    INDEX
    Explanations

    data

    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
     faucet
    -0.09
     penis
    -0.08
     Brot
    -0.08
     trailing
    -0.08
    _damage
    -0.08
     nost
    -0.08
     سرعت
    -0.08
     capped
    -0.08
     ranch
    -0.08
     секрет
    -0.08
    POSITIVE LOGITS
    Ontology
    0.10
    .ecore
    0.10
    predicate
    0.09
    .Predicate
    0.08
     refinement
    0.08
     Delphi
    0.08
     predicate
    0.08
    .Constraint
    0.08
     ontology
    0.08
     classes
    0.08
    Activations Density 0.024%

    No Known Activations