© 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. 54905
    Prev
    Next
    INDEX
    Explanations

    star points

    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
     COMPANY
    -0.08
     GMO
    -0.07
     PLC
    -0.07
    DEM
    -0.07
     questionnaire
    -0.07
     garantizar
    -0.07
     WAY
    -0.07
     sounding
    -0.07
    pakket
    -0.07
     DEM
    -0.07
    POSITIVE LOGITS
     нож
    0.09
    .attack
    0.09
     betray
    0.09
     quarters
    0.09
     limbs
    0.08
     nhau
    0.08
    十四
    0.08
     cauliflower
    0.08
    voit
    0.08
    势
    0.08
    Activations Density 0.019%

    No Known Activations