© 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. 3-RESID-POST-AA
    11. 1482
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plank
    -0.09
     عن
    -0.08
     हुई
    -0.08
    aise
    -0.08
    abril
    -0.08
     plasm
    -0.08
     torrent
    -0.08
    mite
    -0.08
     حز
    -0.08
     plag
    -0.08
    POSITIVE LOGITS
     inhibitors
    0.07
    Alt
    0.07
    conc
    0.07
    Fl
    0.07
    Rad
    0.07
    Wal
    0.07
     helicopter
    0.07
     Transformers
    0.07
    Transform
    0.07
    至少
    0.07
    Activations Density 0.001%

    No Known Activations