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. 12873
    Prev
    Next
    INDEX
    Explanations

    cyclic

    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
     Samba
    -0.08
     Korean
    -0.08
     sterile
    -0.07
     Min
    -0.07
     Telephone
    -0.07
     السلطات
    -0.07
    Telephone
    -0.07
    Min
    -0.07
     sift
    -0.07
     withholding
    -0.07
    POSITIVE LOGITS
     radius
    0.09
     CGRect
    0.08
    Responder
    0.08
    CGRect
    0.08
     ratio
    0.08
     Montes
    0.08
     ail
    0.08
    -floating
    0.08
     BC
    0.08
     counsell
    0.08
    Activations Density 0.004%

    No Known Activations