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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26648
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     HY
    -0.08
    -than
    -0.07
    MC
    -0.07
     satisfe
    -0.07
     SE
    -0.07
    -0.07
    Seeds
    -0.07
     hi
    -0.07
     biomass
    -0.07
     gil
    -0.07
    POSITIVE LOGITS
     இருப்ப
    0.08
     Recall
    0.08
    /constants
    0.08
     recall
    0.07
    그러
    0.07
     Knie
    0.07
     Portsmouth
    0.07
    然而
    0.07
    RESP
    0.07
     삼
    0.07
    Activations Density 0.215%

    No Known Activations