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. 42005
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
     aith
    -0.08
    iple
    -0.08
     boodsch
    -0.08
    hipping
    -0.08
    Bake
    -0.08
     Buch
    -0.08
     hoid
    -0.08
     gly
    -0.07
    ශ්
    -0.07
     compt
    -0.07
    POSITIVE LOGITS
     Пред
    0.08
    DE
    0.08
     Mr
    0.07
    JP
    0.07
     swin
    0.07
    Mr
    0.07
    Dt
    0.07
     motives
    0.07
    vision
    0.07
    NP
    0.07
    Activations Density 0.006%

    No Known Activations