© 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. 94899
    Prev
    Next
    INDEX
    Explanations

    chess

    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
     rose
    -0.08
    占
    -0.07
     గ్ర
    -0.07
     ಗ್ರ
    -0.07
    上涨
    -0.07
     πραγμα
    -0.07
     جودة
    -0.07
     sharp
    -0.07
     ஏ
    -0.07
     ग्र
    -0.07
    POSITIVE LOGITS
     castles
    0.11
     castle
    0.11
    Castle
    0.09
    Juego
    0.09
    fog
    0.08
     congel
    0.08
     spil
    0.08
     anc
    0.08
     pendiente
    0.08
     RESERVED
    0.08
    Activations Density 0.001%

    No Known Activations