© 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. 6111
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ances"

    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
    ilishi
    -0.08
    megiň
    -0.08
    jä
    -0.08
    elp
    -0.08
    yl
    -0.08
     olunur
    -0.07
    eligt
    -0.07
    tać
    -0.07
    zado
    -0.07
    mens
    -0.07
    POSITIVE LOGITS
    ancing
    0.10
    uck
    0.10
    ances
    0.09
    um
    0.08
     Que
    0.08
    asso
    0.08
     switches
    0.08
    оге
    0.08
    âce
    0.08
     repe
    0.08
    Activations Density 0.000%

    No Known Activations