© 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. 18330
    Prev
    Next
    INDEX
    Explanations

    Russian safety descriptions

    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
     düşün
    -0.08
     sights
    -0.08
    oas
    -0.08
    osis
    -0.08
     생각
    -0.08
    ювання
    -0.08
    적인
    -0.08
     shots
    -0.08
     düşünü
    -0.08
    ზე
    -0.08
    POSITIVE LOGITS
    etch
    0.08
    Sibling
    0.08
    (balance
    0.08
     深
    0.07
    0
    0.07
     nerv
    0.07
    Although
    0.07
     profund
    0.07
    同
    0.07
     Extraction
    0.07
    Activations Density 0.000%

    No Known Activations