© 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. 99218
    Prev
    Next
    INDEX
    Explanations

    Business strategy

    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
     ford
    -0.08
    wonder
    -0.08
     reminiscent
    -0.07
     Array
    -0.07
    不仅
    -0.07
     authorities
    -0.07
     Decoder
    -0.07
    Ford
    -0.07
    rop
    -0.07
    -place
    -0.07
    POSITIVE LOGITS
    centaje
    0.11
    'ici
    0.10
    满意
    0.10
     mindst
    0.10
     tilfred
    0.10
    Percentage
    0.10
     durchschnitt
    0.10
    _percentage
    0.09
     gemiddeld
    0.09
     minstens
    0.09
    Activations Density 0.059%

    No Known Activations