© 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. 51260
    Prev
    Next
    INDEX
    Explanations

    quadr

    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
    ‍സ്
    -0.10
     betg
    -0.10
     nepie
    -0.09
     tsis
    -0.09
     thusa
    -0.09
     oceans
    -0.09
    Башҡ
    -0.09
     tsak
    -0.09
    -priced
    -0.09
    ութեան
    -0.09
    POSITIVE LOGITS
    ilateral
    0.31
    il
    0.19
     ABC
    0.18
     quadr
    0.15
     AB
    0.15
     ABD
    0.14
    angle
    0.13
    ilat
    0.13
    ateral
    0.13
    angular
    0.13
    Activations Density 0.017%

    No Known Activations