© 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. 45297
    Prev
    Next
    INDEX
    Explanations

    double-check

    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
    амп
    -0.08
    -dismissible
    -0.08
    есто
    -0.08
     таңда
    -0.08
    ылып
    -0.08
    ест
    -0.07
    маг
    -0.07
    уса
    -0.07
    -elles
    -0.07
    这里只
    -0.07
    POSITIVE LOGITS
     corrobor
    0.10
     reaffirm
    0.09
    .verify
    0.09
     confirm
    0.09
     confirms
    0.09
    .confirm
    0.08
    Confirm
    0.08
     Confirm
    0.08
     reasoning
    0.08
    分析
    0.08
    Activations Density 0.067%

    No Known Activations