© 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. 18470
    Prev
    Next
    INDEX
    Explanations

    unicode

    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
    ែន
    -0.09
    IDX
    -0.08
    Ranges
    -0.08
    ises
    -0.08
     IDX
    -0.08
     ranges
    -0.08
     masturbation
    -0.08
     Initialize
    -0.08
    ssa
    -0.08
    isation
    -0.08
    POSITIVE LOGITS
     cautiously
    0.08
    χω
    0.08
     திற
    0.07
     attraverso
    0.07
     �
    0.07
    ege
    0.07
    uzzi
    0.07
    ffiti
    0.07
     التعامل
    0.07
     दक्ष
    0.07
    Activations Density 0.000%

    No Known Activations