© 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. 19048
    Prev
    Next
    INDEX
    Explanations

    moon

    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
    ционно
    -0.09
    ATOR
    -0.08
     respective
    -0.08
    ेशन
    -0.08
    ERRUP
    -0.08
     usual
    -0.08
    иях
    -0.08
    ORIES
    -0.08
    IMENTO
    -0.08
    ояд
    -0.08
    POSITIVE LOGITS
    lit
    0.18
    light
    0.18
    shine
    0.18
    lighting
    0.16
    beam
    0.15
    rise
    0.15
    stone
    0.13
    cakes
    0.13
    빛
    0.12
    flakes
    0.12
    Activations Density 0.005%

    No Known Activations