© 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. 47614
    Prev
    Next
    INDEX
    Explanations

    replacement character

    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
     eagle
    -0.10
    ército
    -0.09
    arque
    -0.08
     porad
    -0.08
    -powered
    -0.08
     compass
    -0.08
     Eagle
    -0.08
    świ
    -0.08
    mazing
    -0.08
    -effective
    -0.08
    POSITIVE LOGITS
    Functional
    0.08
    Booked
    0.08
    Sched
    0.08
    Hung
    0.08
    FORMAT
    0.08
     Haush
    0.08
    (format
    0.08
    Tu
    0.07
    Paren
    0.07
    nergy
    0.07
    Activations Density 0.000%

    No Known Activations