© 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 EvalsExportsAPI 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. 50309
    Prev
    Next
    INDEX
    Explanations

    se

    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
     Matte
    -0.08
     Britain's
    -0.08
    ிர
    -0.08
    bate
    -0.08
     Sut
    -0.07
     nanos
    -0.07
     wszystkim
    -0.07
     eröff
    -0.07
    ाढ
    -0.07
     emak
    -0.07
    POSITIVE LOGITS
    man
    0.09
    を書く
    0.08
    iyor
    0.07
    IBOutlet
    0.07
    Playable
    0.07
    usus
    0.07
    К
    0.07
     Cock
    0.07
    Wunused
    0.07
    K
    0.07
    Activations Density 0.000%

    No Known Activations