© 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. 18901
    Prev
    Next
    INDEX
    Explanations

    Pok

    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
     "
    -0.09
     `
    -0.08
     också
    -0.08
     также
    -0.08
     også
    -0.08
     תחת
    -0.08
     also
    -0.08
     few
    -0.08
     via
    -0.08
     גם
    -0.08
    POSITIVE LOGITS
    éfono
    0.11
    Phone
    0.11
    ensku
    0.11
    फोन
    0.10
    �்ப
    0.10
    客邦
    0.10
    Pok
    0.10
    lé
    0.10
    pé
    0.09
     Pokémon
    0.09
    Activations Density 0.002%

    No Known Activations