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. 12656
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
     tin
    -0.08
     собой
    -0.08
    lun
    -0.08
     Grave
    -0.07
    qq
    -0.07
    нулся
    -0.07
     pii
    -0.07
     ол
    -0.07
     ribbon
    -0.07
     Bons
    -0.07
    POSITIVE LOGITS
     impeccable
    0.07
    技巧
    0.07
     wisdom
    0.07
     sond
    0.07
    mise
    0.07
     vag
    0.07
    itative
    0.07
     minyak
    0.07
    제를
    0.06
     Wendy
    0.06
    Activations Density 0.018%

    No Known Activations