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. 23-RESID-POST-AA
    6. 98037
    Prev
    Next
    INDEX
    Explanations

    rifle scopes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಕ್ಯ
    -0.09
     క్య
    -0.09
    Unload
    -0.09
     geladen
    -0.08
    �
    -0.08
    امات
    -0.08
     ক্য
    -0.08
     ക്യ
    -0.08
    lav
    -0.08
     Camaro
    -0.08
    POSITIVE LOGITS
     Corre
    0.09
    Corre
    0.09
     corrections
    0.09
     APO
    0.09
     terminal
    0.08
     TV
    0.08
     CEP
    0.08
     hos
    0.08
     correcting
    0.08
    IRON
    0.08
    Activations Density 0.008%

    No Known Activations