© 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. 30200
    Prev
    Next
    INDEX
    Explanations

    quantities with units

    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
     Landsc
    -0.08
     rupa
    -0.08
     entrusted
    -0.08
    优势
    -0.08
     predictable
    -0.08
    _sequences
    -0.08
     manageable
    -0.08
     сю
    -0.08
     जिम्म
    -0.08
    streams
    -0.08
    POSITIVE LOGITS
    Units
    0.10
     units
    0.09
    units
    0.09
    Calories
    0.09
     Units
    0.08
     feet
    0.08
     Calories
    0.08
     Unit
    0.07
    /year
    0.07
    ั่วโมง
    0.07
    Activations Density 0.026%

    No Known Activations