© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68267
    Prev
    Next
    INDEX
    Explanations

    elements

    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
     Scripture
    -0.09
     conversational
    -0.09
     fiel
    -0.08
     SVG
    -0.08
    atisfied
    -0.08
    .du
    -0.08
    .email
    -0.08
     policy
    -0.08
     rhetoric
    -0.08
     Happy
    -0.08
    POSITIVE LOGITS
     exotic
    0.10
     synthesized
    0.10
     stabilization
    0.10
     Exotic
    0.09
     нест
    0.09
     stabilized
    0.09
     extremadamente
    0.09
     sínt
    0.09
     nonexistent
    0.08
    entered
    0.08
    Activations Density 0.004%

    No Known Activations