© 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. 50428
    Prev
    Next
    INDEX
    Explanations

    Penicillin

    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
     fungal
    -0.13
     bacterial
    -0.11
     antiviral
    -0.11
     microbial
    -0.10
     fungus
    -0.10
     antimicrobial
    -0.10
     yeast
    -0.10
    fung
    -0.10
     antiv
    -0.10
     fungi
    -0.10
    POSITIVE LOGITS
     ce
    0.13
     pen
    0.12
     am
    0.11
     Pen
    0.11
    pen
    0.10
     Ce
    0.10
     betal
    0.10
    Pen
    0.10
    ce
    0.10
     Clar
    0.10
    Activations Density 0.003%

    No Known Activations