© 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. 51106
    Prev
    Next
    INDEX
    Explanations

    h

    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
     dc
    -0.08
     탐
    -0.08
     ബാല
    -0.08
     количе
    -0.07
     ശേഷ
    -0.07
    иш
    -0.07
    udha
    -0.07
    =d
    -0.07
    dc
    -0.07
    ，即
    -0.07
    POSITIVE LOGITS
     tass
    0.08
    @Mapper
    0.08
    CLUSION
    0.08
    ойд
    0.08
    ёни
    0.08
    нали
    0.08
     bestimm
    0.08
    .of
    0.07
     Gns
    0.07
    []);↵
    0.07
    Activations Density 0.000%

    No Known Activations