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. 8865
    Prev
    Next
    INDEX
    Explanations

    Geometry incircles touchpoints

    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
     Samp
    -0.09
     Om
    -0.08
     Colonial
    -0.08
    (errors
    -0.08
    &S
    -0.08
     militant
    -0.08
     criminal
    -0.07
     المكت
    -0.07
     answers
    -0.07
    .clients
    -0.07
    POSITIVE LOGITS
     भेट
    0.09
    warden
    0.08
    径
    0.08
    дары
    0.07
     கத
    0.07
    的位置
    0.07
     washers
    0.07
     парков
    0.07
    дарын
    0.07
     कार
    0.07
    Activations Density 0.012%

    No Known Activations