© 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. 129551
    Prev
    Next
    INDEX
    Explanations

    CUDA

    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
     내
    -0.08
     spontaneous
    -0.08
     spontaneously
    -0.08
    -screen
    -0.07
    润
    -0.07
    itarian
    -0.07
    cobra
    -0.07
    aniro
    -0.07
    .Lerp
    -0.07
     bald
    -0.07
    POSITIVE LOGITS
    Mis
    0.08
     katanya
    0.07
    Stan
    0.07
    �
    0.07
     lic
    0.07
    worker
    0.07
     Load
    0.07
    _SUPPORT
    0.07
     calend
    0.07
    Confirmed
    0.07
    Activations Density 0.001%

    No Known Activations