© 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. 11-RESID-POST-AA
    11. 94987
    Prev
    Next
    INDEX
    Explanations

    sauna

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     campagnes
    -0.08
     funding
    -0.08
     lawsuits
    -0.07
    .bounding
    -0.07
    日前
    -0.07
    Never
    -0.07
    転
    -0.07
     mû
    -0.07
    ameras
    -0.07
     emball
    -0.07
    POSITIVE LOGITS
     sauna
    0.13
     sweating
    0.11
     Sauna
    0.10
     sala
    0.10
     salas
    0.09
     कमरे
    0.08
     �
    0.08
     enkel
    0.08
    汗
    0.08
     Hum
    0.08
    Activations Density 0.003%

    No Known Activations