© 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. 24671
    Prev
    Next
    INDEX
    Explanations

    描述

    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
     publishes
    -0.08
     Publ
    -0.08
    _pub
    -0.08
     Radius
    -0.08
     Magnetic
    -0.08
     Mouse
    -0.07
    Publ
    -0.07
    .mouse
    -0.07
    ysters
    -0.07
     Satellite
    -0.07
    POSITIVE LOGITS
     expressão
    0.09
     предыдущ
    0.08
     shorter
    0.08
    IDDLE
    0.08
     আত্ম
    0.08
     transcripts
    0.08
    υτό
    0.08
     нис
    0.08
     выраз
    0.08
     vergang
    0.08
    Activations Density 0.000%

    No Known Activations