© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97287
    Prev
    Next
    INDEX
    Explanations

    say "lood"

    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
    Esp
    -0.08
    нав
    -0.07
     sensor
    -0.07
     forecasting
    -0.07
    (co
    -0.07
     консульта
    -0.07
    EMENT
    -0.07
     emphasized
    -0.07
    oking
    -0.07
    engu
    -0.06
    POSITIVE LOGITS
     Carm
    0.08
    bums
    0.07
    .favorite
    0.07
    �
    0.07
    fab
    0.07
    lood
    0.07
    �
    0.07
    inic
    0.07
     verlor
    0.07
    territ
    0.07
    Activations Density 0.000%

    No Known Activations