© 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. 29676
    Prev
    Next
    INDEX
    Explanations

    Foam, foam-roll

    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
     منظ
    -0.08
     cardinal
    -0.07
     blooms
    -0.07
     angles
    -0.07
    atched
    -0.07
     accommodates
    -0.07
     routes
    -0.07
    cto
    -0.06
     Jan
    -0.06
     contrasts
    -0.06
    POSITIVE LOGITS
     жұмы
    0.10
    .scroll
    0.09
    .Scroll
    0.09
    Ｆ
    0.09
    /self
    0.09
     sidewalk
    0.09
    _SCROLL
    0.09
     treadmill
    0.09
     Homemade
    0.09
     homemade
    0.08
    Activations Density 0.001%

    No Known Activations