© 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. 96322
    Prev
    Next
    INDEX
    Explanations

    Alpha

    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
    ್ಳ
    -0.09
    _INCLUDED
    -0.08
     скаж
    -0.08
    iculas
    -0.08
     Hmm
    -0.08
    198
    -0.08
     चली
    -0.08
     sel
    -0.07
    upos
    -0.07
     sobra
    -0.07
    POSITIVE LOGITS
    Go
    0.11
     male
    0.11
    Zero
    0.10
    numeric
    0.10
    Fold
    0.10
    Male
    0.10
    Numeric
    0.10
     Male
    0.10
     female
    0.09
    male
    0.09
    Activations Density 0.004%

    No Known Activations