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. 30036
    Prev
    Next
    INDEX
    Explanations

    rearrange

    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
    fax
    -0.09
    .REQUEST
    -0.08
     preced
    -0.08
     preceded
    -0.07
    Handled
    -0.07
    brot
    -0.07
     REQUEST
    -0.07
    واره
    -0.07
    executor
    -0.07
     happening
    -0.07
    POSITIVE LOGITS
     reorgan
    0.09
     rearr
    0.09
    sembling
    0.09
    Arrangement
    0.08
     करून
    0.08
     arrangement
    0.08
    orientation
    0.08
     assembling
    0.08
     orientations
    0.08
     collage
    0.08
    Activations Density 0.010%

    No Known Activations