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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 104308
    Prev
    Next
    INDEX
    Explanations

    3

    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
     biste
    -0.09
     Suz
    -0.08
     Tako
    -0.08
    কর
    -0.08
     mimo
    -0.08
    hern
    -0.07
    บิน
    -0.07
     Kai
    -0.07
     angust
    -0.07
     poza
    -0.07
    POSITIVE LOGITS
     cents
    0.08
     akt
    0.07
     laman
    0.07
     undo
    0.07
    Cancel
    0.07
     बाकी
    0.07
     cadeaux
    0.07
    =parse
    0.07
     cent
    0.07
     pennies
    0.07
    Activations Density 0.054%

    No Known Activations