Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90091
    Prev
    Next
    INDEX
    Explanations

    <|end|>

    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
     â
    -0.11
     Ï
    -0.09
    â
    -0.09
    .Â
    -0.08
    (mm
    -0.08
    /SP
    -0.08
    /St
    -0.07
    Ï
    -0.07
     Î
    -0.07
    (TR
    -0.07
    POSITIVE LOGITS
     Idle
    0.08
    }↵↵↵↵/
    0.08
    >↵↵↵↵
    0.08
    }↵↵↵↵
    0.08
    };↵↵↵↵
    0.07
     polygon
    0.07
     externe
    0.07
     coil
    0.07
     topp
    0.07
     pente
    0.07
    Activations Density 0.080%

    No Known Activations