© 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. 78988
    Prev
    Next
    INDEX
    Explanations

    inverse

    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
     Goose
    -0.09
    NG
    -0.09
    ng
    -0.08
     goose
    -0.08
     níveis
    -0.07
     niveaux
    -0.07
     mis
    -0.07
     mil
    -0.07
    falls
    -0.07
    enar
    -0.07
    POSITIVE LOGITS
     modulo
    0.09
     Since
    0.08
     восстанов
    0.08
     ари
    0.08
     Kred
    0.08
     Concentr
    0.08
     Dé
    0.07
     hashmap
    0.07
     Kredit
    0.07
    -css
    0.07
    Activations Density 0.010%

    No Known Activations