© 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. 68266
    Prev
    Next
    INDEX
    Explanations

    ligand field

    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
     bert
    -0.07
     مه
    -0.07
    afet
    -0.07
     қилин
    -0.07
     ნ
    -0.07
     lots
    -0.07
     formatter
    -0.07
    )null
    -0.07
    _construct
    -0.07
     ingredient
    -0.07
    POSITIVE LOGITS
    ，因为
    0.09
    endl
    0.08
    slash
    0.08
    Slash
    0.07
    ění
    0.07
    ，两
    0.07
    扫码
    0.07
     dislikes
    0.07
    DOMContent
    0.07
     reluct
    0.07
    Activations Density 0.001%

    No Known Activations