Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49086
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
     المغرب
    -0.09
     italiani
    -0.08
     Pompe
    -0.08
    	CC
    -0.08
     perifer
    -0.08
     DEAD
    -0.08
    SON
    -0.08
     patrim
    -0.08
     günd
    -0.08
     OT
    -0.08
    POSITIVE LOGITS
     itself
    0.08
     Himself
    0.07
     wiederum
    0.07
    uir
    0.07
    iscal
    0.07
    isa
    0.07
    adar
    0.07
    *j
    0.07
     તરફ
    0.07
     kaut
    0.07
    Activations Density 0.154%

    No Known Activations