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. 76121
    Prev
    Next
    INDEX
    Explanations

    angle

    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
     Schl
    -0.09
    .lines
    -0.08
    -social
    -0.08
    odne
    -0.08
    .low
    -0.08
    .literal
    -0.08
    .ll
    -0.07
    SL
    -0.07
    -low
    -0.07
    ொட
    -0.07
    POSITIVE LOGITS
     
    0.08
     angle
    0.08
     जी
    0.08
     Kaw
    0.08
     between
    0.07
     trz
    0.07
     radians
    0.07
     
    0.07
     RAD
    0.07
     Dh
    0.07
    Activations Density 0.014%

    No Known Activations