© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    say non-English 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
    ULL
    -0.08
    ull
    -0.08
    oir
    -0.08
     вип
    -0.08
     வெளிய
    -0.08
    ulls
    -0.08
     вып
    -0.07
     extinct
    -0.07
     einschließlich
    -0.07
     моей
    -0.07
    POSITIVE LOGITS
    уж
    0.10
    oble
    0.10
    ன்று
    0.10
    ec
    0.09
    ന്ന്
    0.09
    oboye
    0.09
    ice
    0.09
    िति
    0.09
    ్ణ
    0.09
    मत
    0.08
    Activations Density 0.008%

    No Known Activations