© 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. 48625
    Prev
    Next
    INDEX
    Explanations

    Foreign language

    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
    ek
    -0.10
    lık
    -0.09
    otype
    -0.09
    ování
    -0.09
     An
    -0.09
    omorphic
    -0.09
    okr
    -0.08
    lamak
    -0.08
    ovar
    -0.08
    ova
    -0.08
    POSITIVE LOGITS
    ális
    0.10
    álně
    0.10
    ální
    0.10
    álních
    0.10
    ally
    0.09
    ированный
    0.09
    álne
    0.09
    ологических
    0.09
    arlo
    0.08
    ирована
    0.08
    Activations Density 0.006%

    No Known Activations