© 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. 23-RESID-POST-AA
    11. 50804
    Prev
    Next
    INDEX
    Explanations

    Asp

    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
     leader
    -0.08
     accelerated
    -0.08
    éd
    -0.08
    ández
    -0.08
    ourses
    -0.08
    ippings
    -0.08
    itores
    -0.07
    ništ
    -0.07
    ionais
    -0.07
    ấp
    -0.07
    POSITIVE LOGITS
    ર્જ
    0.09
    iration
    0.09
    өк
    0.09
    etar
    0.09
    ective
    0.09
    ेक्ट
    0.08
    iring
    0.08
    েক
    0.08
    etti
    0.07
    ેક્ટ
    0.07
    Activations Density 0.001%

    No Known Activations