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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99052
    Prev
    Next
    INDEX
    Explanations

    Math/Numbers

    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
     Donner
    -0.08
     vaccination
    -0.08
     Zagre
    -0.08
     turma
    -0.08
     tournament
    -0.08
    ్జ
    -0.07
     చిక
    -0.07
    ميس
    -0.07
     nim
    -0.07
     Saraje
    -0.07
    POSITIVE LOGITS
     Intern
    0.08
     &_
    0.08
     rinc
    0.08
     DOI
    0.08
     yen
    0.08
     lul
    0.07
    Intern
    0.07
    Granted
    0.07
     blank
    0.07
     Toolkit
    0.07
    Activations Density 0.012%

    No Known Activations