© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    )d

    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
    's
    -0.11
    -based
    -0.09
    ":"",↵
    -0.09
    :"",↵
    -0.09
    ’étais
    -0.09
    È
    -0.09
     is
    -0.08
     als
    -0.08
    -only
    -0.08
     kitu
    -0.08
    POSITIVE LOGITS
     όπου
    0.13
     जहाँ
    0.13
     જ્યાં
    0.13
     où
    0.13
     जहां
    0.13
     where
    0.13
     جہاں
    0.12
     donde
    0.12
     כאשר
    0.12
     где
    0.12
    Activations Density 0.080%

    No Known Activations