© 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. 18955
    Prev
    Next
    INDEX
    Explanations

    cond

    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
     kinds
    -0.09
    ODES
    -0.08
     anderem
    -0.07
    оте
    -0.07
     ик
    -0.07
     maintains
    -0.07
     ilg
    -0.07
    berta
    -0.07
     aanvraag
    -0.07
     drugim
    -0.07
    POSITIVE LOGITS
    ensation
    0.18
    ensing
    0.18
    ensed
    0.17
    enses
    0.14
    ense
    0.13
    iciones
    0.13
    enseur
    0.13
    icional
    0.12
    icions
    0.11
    enced
    0.11
    Activations Density 0.008%

    No Known Activations