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. 113953
    Prev
    Next
    INDEX
    Explanations

    Post-void residual

    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
    変更
    -0.09
    alink
    -0.08
    寿
    -0.08
     typename
    -0.08
     변경
    -0.08
     hustle
    -0.07
     manches
    -0.07
     lifecycle
    -0.07
    hostname
    -0.07
    vs
    -0.07
    POSITIVE LOGITS
     catheter
    0.10
     vaginal
    0.09
     manually
    0.08
    úd
    0.08
     forcibly
    0.08
     самостоятельно
    0.08
     Kū
    0.08
     पकड़
    0.08
     voluntarily
    0.08
     использ
    0.08
    Activations Density 0.004%

    No Known Activations