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. 7-RESID-POST-AA
    6. 131059
    Prev
    Next
    INDEX
    Explanations

    circumstances and opportunities happening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basal
    -0.07
     Han
    -0.07
    HAR
    -0.07
     počet
    -0.07
     munch
    -0.07
     Plateau
    -0.07
    Pri
    -0.07
    odian
    -0.07
     restantes
    -0.07
    회원
    -0.07
    POSITIVE LOGITS
     যেমন
    0.09
    �
    0.09
     כגון
    0.08
    比如
    0.08
     कल्प
    0.08
     mundane
    0.08
    ,比如
    0.08
     вроде
    0.08
     яң
    0.08
     przedsi
    0.08
    Activations Density 0.370%

    No Known Activations