© 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. 49990
    Prev
    Next
    INDEX
    Explanations

    Prime factorization with 1001

    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
     Heat
    -0.09
    56
    -0.08
    560
    -0.08
    Heat
    -0.08
    -0.08
    ərinin
    -0.07
    �
    -0.07
    561
    -0.07
    -ar
    -0.07
    anaan
    -0.07
    POSITIVE LOGITS
     pratic
    0.09
    0.08
    jev
    0.08
    sold
    0.08
     absol
    0.08
    山区
    0.07
    absolute
    0.07
    bounded
    0.07
    particularly
    0.07
    uthuk
    0.07
    Activations Density 0.003%
    No Known Activations