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. 45872
    Prev
    Next
    INDEX
    Explanations

    sound

    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
     suggests
    -0.08
     directing
    -0.08
     Тем
    -0.07
     Vander
    -0.07
     survives
    -0.07
    —
    -0.07
    って
    -0.07
    体
    -0.07
    て
    -0.07
     ref
    -0.07
    POSITIVE LOGITS
    》、《
    0.09
     lyst
    0.08
    ”,“
    0.08
     luogo
    0.08
     entrevista
    0.08
     hingegen
    0.08
    uchi
    0.08
    ”、“
    0.08
     కాదు
    0.07
     ovu
    0.07
    Activations Density 0.293%

    No Known Activations