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. 23288
    Prev
    Next
    INDEX
    Explanations

    implied

    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
     문자열
    -0.09
    Leaderboard
    -0.08
     counsell
    -0.08
    雪
    -0.08
    -0.08
     asteroid
    -0.08
    _AXI
    -0.08
     člov
    -0.08
    .aw
    -0.07
    _axi
    -0.07
    POSITIVE LOGITS
    暗
    0.08
     implicit
    0.08
     savent
    0.08
     implied
    0.08
    irg
    0.08
     implicitly
    0.08
     quantities
    0.08
     ukuthi
    0.07
     ότι
    0.07
     pressup
    0.07
    Activations Density 0.020%

    No Known Activations