© 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. 6503
    Prev
    Next
    INDEX
    Explanations

    say "ification" ending

    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
    ur
    -0.09
    ्थ
    -0.09
    ir
    -0.09
    pher
    -0.09
    irim
    -0.08
    цию
    -0.08
    cter
    -0.08
    ции
    -0.08
    eriya
    -0.08
    xz
    -0.08
    POSITIVE LOGITS
    raînement
    0.11
    êtement
    0.10
    鏈
    0.08
    ête
    0.08
    UNI
    0.08
     veni
    0.08
    链
    0.08
     traite
    0.08
    Mailbox
    0.08
    nonce
    0.08
    Activations Density 0.000%

    No Known Activations