© 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. 50954
    Prev
    Next
    INDEX
    Explanations

    ting

    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
    ഖ്യാപ
    -0.08
    Ј
    -0.08
     Nakam
    -0.08
    ј
    -0.08
    VEY
    -0.07
    QUENCE
    -0.07
     renovation
    -0.07
    NAPSHOT
    -0.07
    792
    -0.07
     Eğitim
    -0.07
    POSITIVE LOGITS
    to
    0.08
    le
    0.08
    -to
    0.08
    intaan
    0.08
     bases
    0.08
     residues
    0.08
    ones
    0.07
    Resid
    0.07
    aes
    0.07
    _to
    0.07
    Activations Density 0.003%

    No Known Activations