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. 119369
    Prev
    Next
    INDEX
    Explanations

    positive attributes

    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
     juli
    -0.09
     darf
    -0.08
    .includes
    -0.08
    .Can
    -0.07
    �
    -0.07
     znam
    -0.07
     Fill
    -0.07
    ोल
    -0.07
    yas
    -0.07
    .SE
    -0.07
    POSITIVE LOGITS
     demais
    0.11
     incorrectly
    0.10
    못
    0.10
     unsuccess
    0.10
    不到
    0.10
     алмай
    0.10
     incap
    0.09
     hopefully
    0.09
    但是
    0.09
     wrongly
    0.09
    Activations Density 0.979%

    No Known Activations