© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19111
    Prev
    Next
    INDEX
    Explanations

    result

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bọ
    -0.09
    emde
    -0.09
     toilets
    -0.08
     ধরনের
    -0.08
     wipes
    -0.08
    utane
    -0.08
    ongan
    -0.08
     slags
    -0.08
    emet
    -0.08
    icken
    -0.08
    POSITIVE LOGITS
     result
    0.15
     Result
    0.14
    	result
    0.13
     RESULT
    0.13
     résultat
    0.13
    _result
    0.13
     αποτέλεσμα
    0.13
     resultado
    0.13
     výsled
    0.13
     результат
    0.12
    Activations Density 0.001%

    No Known Activations