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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96370
    Prev
    Next
    INDEX
    Explanations

    --

    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
    ston
    -0.08
    nij
    -0.08
    sf
    -0.07
     so
    -0.07
    rec
    -0.07
     from
    -0.07
    ring
    -0.07
     aussi
    -0.07
     originating
    -0.07
    incer
    -0.07
    POSITIVE LOGITS
    _VOL
    0.09
     volts
    0.08
    .vol
    0.08
    _unsigned
    0.08
    ضغط
    0.08
    _candidate
    0.08
    .mod
    0.08
    еклама
    0.08
     Seeds
    0.08
     deepcopy
    0.08
    Activations Density 0.000%

    No Known Activations