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. 102972
    Prev
    Next
    INDEX
    Explanations

    self-harm habits

    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
     Oxygen
    -0.08
     "*"
    -0.08
     [{"
    -0.08
     declaração
    -0.08
     oxygen
    -0.07
     '*'
    -0.07
     outwe
    -0.07
    oxygen
    -0.07
     isol
    -0.07
     calculate
    -0.07
    POSITIVE LOGITS
     lace
    0.08
     gây
    0.08
    nop
    0.08
    .Ch
    0.08
    .H
    0.08
     pests
    0.08
    .dest
    0.08
     mène
    0.08
    �
    0.08
     vicious
    0.07
    Activations Density 0.008%

    No Known Activations