© 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. 19-RESID-POST-AA
    11. 102707
    Prev
    Next
    INDEX
    Explanations

    lif

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ített
    -0.09
    ורים
    -0.08
    ী
    -0.08
     ital
    -0.08
     משפ
    -0.08
    革命
    -0.08
    izzati
    -0.08
    িতা
    -0.08
    िता
    -0.08
    ირ
    -0.08
    POSITIVE LOGITS
    esize
    0.12
    elong
    0.11
    estanding
    0.10
    etimes
    0.10
    elines
    0.10
    eliness
    0.10
    shots
    0.09
    nads
    0.09
    kọta
    0.09
    tings
    0.09
    Activations Density 0.002%

    No Known Activations