© 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. 50833
    Prev
    Next
    INDEX
    Explanations

    rella

    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
     ATTR
    -0.08
     bewonder
    -0.08
    OUR
    -0.07
    wię
    -0.07
    ্ব
    -0.07
    pozn
    -0.07
     jit
    -0.07
    버
    -0.07
     MAK
    -0.07
    bz
    -0.07
    POSITIVE LOGITS
    rella
    0.13
    rellas
    0.13
    ication
    0.11
    icación
    0.11
    ications
    0.10
    icanos
    0.10
    icação
    0.10
    ുണ്ട
    0.09
    ICATION
    0.09
     hele
    0.08
    Activations Density 0.003%

    No Known Activations