© 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. 18564
    Prev
    Next
    INDEX
    Explanations

    mixed content texts

    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
     қандақ
    -0.10
     կողմ
    -0.10
    ՞նչ
    -0.10
     марказ
    -0.10
     сиёс
    -0.09
     бутлуур
    -0.09
     буз
    -0.09
     որի
    -0.09
     көңүл
    -0.09
     hallway
    -0.09
    POSITIVE LOGITS
     imitate
    0.07
     (~
    0.07
     तुल
    0.07
     Prompt
    0.07
    0.07
     ratios
    0.07
     Rat
    0.07
    ird
    0.07
    某
    0.07
    與
    0.07
    Activations Density 0.000%
    No Known Activations