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. 43506
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     ambient
    -0.10
    Ambient
    -0.10
     Ambient
    -0.09
     സംസ
    -0.08
    Arena
    -0.08
    Pid
    -0.08
    atif
    -0.07
    strcmp
    -0.07
     livelihood
    -0.07
    Archived
    -0.07
    POSITIVE LOGITS
    位置
    0.10
     positions
    0.10
    .positions
    0.09
    positions
    0.09
     perpendicular
    0.09
    _positions
    0.09
     Positions
    0.09
     위치
    0.08
     CGPoint
    0.08
    的位置
    0.08
    Activations Density 0.061%

    No Known Activations