© 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. 23-RESID-POST-AA
    11. 51871
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
    ลี่ย
    -0.09
     dhin
    -0.08
     koo
    -0.07
     pamoja
    -0.07
     doubtful
    -0.07
     bamwe
    -0.07
    -0.07
     جهت
    -0.07
     mõned
    -0.07
     سوء
    -0.06
    POSITIVE LOGITS
     exactly
    0.73
     exactamente
    0.68
     exactement
    0.66
     Exactly
    0.66
     exatamente
    0.65
    Exactly
    0.63
     precies
    0.62
     precisely
    0.61
    exact
    0.61
     EXACT
    0.60
    Activations Density 1.147%

    No Known Activations