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. 76060
    Prev
    Next
    INDEX
    Explanations

    Academia

    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
     astronomical
    -0.08
     astronom
    -0.08
     gamm
    -0.08
     Twain
    -0.07
    �
    -0.07
     astronomy
    -0.07
     TEL
    -0.07
     Perl
    -0.07
     Misc
    -0.07
     מט
    -0.07
    POSITIVE LOGITS
     presenti
    0.09
    Skeleton
    0.08
     kotlinx
    0.08
    -grad
    0.08
     praesent
    0.08
    арм
    0.08
     neckline
    0.08
     incline
    0.08
     underway
    0.08
     presentes
    0.08
    Activations Density 0.004%

    No Known Activations