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. 58958
    Prev
    Next
    INDEX
    Explanations

    your/my

    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
     votação
    -0.08
     ваканс
    -0.08
     típ
    -0.08
     calculations
    -0.08
    Raid
    -0.08
    itura
    -0.08
     Raid
    -0.07
    _ru
    -0.07
     તમ
    -0.07
     рецеп
    -0.07
    POSITIVE LOGITS
    当前
    0.08
     teens
    0.07
    273
    0.07
     steadily
    0.07
     Lus
    0.07
    -dependent
    0.07
    整体
    0.07
    เอง
    0.07
    မွ
    0.07
    ского
    0.07
    Activations Density 0.071%

    No Known Activations