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. 29832
    Prev
    Next
    INDEX
    Explanations

    bowl

    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
     Comments
    -0.08
    _INPUT
    -0.08
    酒
    -0.08
     Wines
    -0.08
    COMMENTS
    -0.08
     Floyd
    -0.08
     coats
    -0.08
     finesse
    -0.07
    stdafx
    -0.07
     Entrance
    -0.07
    POSITIVE LOGITS
     nutritious
    0.10
    (lhs
    0.09
     salads
    0.09
     lhs
    0.09
     komplex
    0.09
    akta
    0.09
     mediterr
    0.09
     ಅನ್ನ
    0.08
     greens
    0.08
    ази
    0.08
    Activations Density 0.019%

    No Known Activations