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. 65731
    Prev
    Next
    INDEX
    Explanations

    moral scenarios

    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
    /MPL
    -0.08
     auxiliar
    -0.08
     birt
    -0.07
     annum
    -0.07
     BL
    -0.07
    .Pattern
    -0.07
     exacte
    -0.07
     ded
    -0.07
     RANGE
    -0.07
     ș
    -0.06
    POSITIVE LOGITS
     Holocaust
    0.09
     :)↵↵
    0.09
     unnecessarily
    0.08
     preparedness
    0.08
     :)↵
    0.08
     torture
    0.08
    umbing
    0.08
     veldig
    0.08
     dictator
    0.08
    Doing
    0.07
    Activations Density 0.011%

    No Known Activations