© 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. 23-RESID-POST-AA
    11. 97454
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rodents
    -0.10
     Rod
    -0.09
     Caracas
    -0.09
     rats
    -0.09
    Rod
    -0.09
     Dermat
    -0.08
     rat
    -0.08
     dermatologist
    -0.08
     Wall
    -0.08
     hashtags
    -0.08
    POSITIVE LOGITS
     viento
    0.08
     xm
    0.08
    Vm
    0.07
     espíritu
    0.07
    auto
    0.07
     volk
    0.07
     airy
    0.07
     szt
    0.07
     sola
    0.07
     mimo
    0.07
    Activations Density 0.005%

    No Known Activations