© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64549
    Prev
    Next
    INDEX
    Explanations

    temporary

    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
    ొక్క
    -0.08
     واک
    -0.08
     ঠিক
    -0.08
    -[
    -0.08
     همچ
    -0.08
    =d
    -0.08
     مراق
    -0.08
     nutshell
    -0.08
     اصلی
    -0.08
    _nc
    -0.08
    POSITIVE LOGITS
     laden
    0.09
     Contest
    0.08
     ular
    0.07
    Load
    0.07
    rat
    0.07
    ething
    0.07
     geladen
    0.07
     contests
    0.07
    tex
    0.07
    Conversation
    0.07
    Activations Density 0.001%

    No Known Activations