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. 325
    Prev
    Next
    INDEX
    Explanations

    batch files

    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
     phy
    -0.09
     favored
    -0.09
     concret
    -0.08
    成熟
    -0.08
    EOS
    -0.08
    Classification
    -0.08
     democr
    -0.08
     ops
    -0.08
    phy
    -0.08
    olm
    -0.08
    POSITIVE LOGITS
    .exe
    0.12
     VBA
    0.11
    scht
    0.11
     scripting
    0.10
     freeware
    0.10
     DOS
    0.09
     exited
    0.09
     терп
    0.09
     aliases
    0.09
     Trails
    0.09
    Activations Density 0.017%

    No Known Activations