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. 109351
    Prev
    Next
    INDEX
    Explanations

    number

    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
    logs
    -0.08
    itha
    -0.08
     outer
    -0.08
    alus
    -0.08
    Outer
    -0.08
     logs
    -0.08
     alguma
    -0.08
     கண
    -0.07
     Scho
    -0.07
     отношение
    -0.07
    POSITIVE LOGITS
     wenige
    0.12
     handful
    0.11
     wenigen
    0.11
    几个
    0.10
     few
    0.10
     thôi
    0.10
     pochi
    0.09
    能够
    0.09
     sahaja
    0.09
     finit
    0.09
    Activations Density 0.052%

    No Known Activations