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

    Neuronpedia

    APICircuit 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. 60736
    Prev
    Next
    INDEX
    Explanations

    different

    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
     Windows
    -0.08
     potential
    -0.07
     coverage
    -0.07
     guided
    -0.07
     cobertura
    -0.07
    <vector
    -0.07
     human
    -0.07
    -mf
    -0.07
     signal
    -0.07
     Canton
    -0.07
    POSITIVE LOGITS
     না
    0.10
     тоғ
    0.09
     несп
    0.09
     الني
    0.09
     distint
    0.09
     তিন
    0.09
     тәс
    0.08
    besch
    0.08
     الثلاث
    0.08
    三个
    0.08
    Activations Density 0.022%

    No Known Activations