© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96854
    Prev
    Next
    INDEX
    Explanations

    cosine calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Showing
    -0.08
     cheg
    -0.07
     open
    -0.07
     Writing
    -0.07
     C
    -0.07
    +C
    -0.07
     formatted
    -0.07
     आउट
    -0.07
    Formatted
    -0.07
     AG
    -0.07
    POSITIVE LOGITS
    fusion
    0.12
    extract
    0.10
    resolve
    0.09
    keys
    0.09
    exam
    0.09
    ifft
    0.09
    Fusion
    0.09
    join
    0.09
     qi
    0.08
    iceps
    0.08
    Activations Density 0.000%

    No Known Activations