© 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. 18439
    Prev
    Next
    INDEX
    Explanations

    cross

    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
     JSImport
    -0.09
     جنوب
    -0.09
     if
    -0.09
     pued
    -0.09
    ACHED
    -0.08
    ALTH
    -0.08
     نفت
    -0.08
    τυνομ
    -0.08
    ��
    -0.08
     poud
    -0.08
    POSITIVE LOGITS
     ratio
    0.15
     ratios
    0.14
    ratio
    0.13
    Ratio
    0.12
    relation
    0.11
     Ratio
    0.11
    _ratio
    0.11
     verhouding
    0.10
    product
    0.10
     отношении
    0.10
    Activations Density 0.003%

    No Known Activations