© 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 EvalsExportsAPI 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. 49504
    Prev
    Next
    INDEX
    Explanations

    acoustic

    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
     accrued
    -0.09
    andos
    -0.09
     acum
    -0.09
     acidic
    -0.08
     aerobic
    -0.08
    _ac
    -0.08
     acute
    -0.08
     koris
    -0.08
     Acquisition
    -0.08
    zés
    -0.07
    POSITIVE LOGITS
     guitar
    0.11
    -electric
    0.10
     guitars
    0.10
     Guitar
    0.10
    Scenes
    0.08
    .pnl
    0.08
    ്സ
    0.08
    икалық
    0.08
    -transparent
    0.08
     panneau
    0.08
    Activations Density 0.003%

    No Known Activations