© 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. 99261
    Prev
    Next
    INDEX
    Explanations

    s

    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
    ồm
    -0.08
    _movies
    -0.08
    扎
    -0.07
    上映
    -0.07
    xa
    -0.07
    рами
    -0.07
     estaban
    -0.07
    북
    -0.07
    .movies
    -0.07
     movies
    -0.07
    POSITIVE LOGITS
     kennt
    0.09
    障
    0.08
     kez
    0.08
    ceil
    0.08
     notoriously
    0.07
    电�
    0.07
     perso
    0.07
     costly
    0.07
     Apar
    0.07
     coût
    0.07
    Activations Density 0.008%

    No Known Activations