© 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. 129407
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients

    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
     помещения
    -0.08
     अन्तर
    -0.08
     warmte
    -0.07
    Temper
    -0.07
     temperament
    -0.07
     flatter
    -0.07
     ARCH
    -0.07
    Nam
    -0.07
    절
    -0.07
     трубы
    -0.07
    POSITIVE LOGITS
     trail
    0.08
     Explosion
    0.08
     slain
    0.07
     endforeach
    0.07
     laver
    0.07
     mortos
    0.07
    -Free
    0.07
     prij
    0.07
     Sprinkle
    0.07
     functools
    0.07
    Activations Density 0.013%

    No Known Activations