© 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. 49919
    Prev
    Next
    INDEX
    Explanations

    t

    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
    Target
    -0.08
    .cc
    -0.08
     börja
    -0.07
    CC
    -0.07
    SI
    -0.07
    Ment
    -0.07
     cc
    -0.07
    Early
    -0.07
    annies
    -0.07
    _delta
    -0.07
    POSITIVE LOGITS
    DEF
    0.08
    óm
    0.08
    рать
    0.08
    なお
    0.08
    ίνει
    0.08
     ご
    0.08
     KP
    0.08
     dañ
    0.08
    omen
    0.08
     נת
    0.08
    Activations Density 0.000%

    No Known Activations