© 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. 95301
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    /int
    -0.08
     decom
    -0.08
    _DECLARE
    -0.07
    èy
    -0.07
     ENTER
    -0.07
     advocates
    -0.07
    提示
    -0.07
     technically
    -0.07
     attentive
    -0.07
    -0.07
    POSITIVE LOGITS
    cdnjs
    0.14
     CDN
    0.13
    maxcdn
    0.11
    cdn
    0.11
    stackpath
    0.11
    .jsdelivr
    0.10
     alojamiento
    0.09
     Hosted
    0.09
     hosped
    0.09
    Hosted
    0.09
    Activations Density 0.005%
    No Known Activations