© 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. 50371
    Prev
    Next
    INDEX
    Explanations

    K

    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
    Autocomplete
    -0.08
    ентар
    -0.07
    իր
    -0.07
    .Destroy
    -0.07
    ITOS
    -0.07
    ावरण
    -0.07
    дат
    -0.07
    ENDIF
    -0.07
     uitvoeren
    -0.07
     dě
    -0.07
    POSITIVE LOGITS
    ebab
    0.10
    way
    0.09
    hao
    0.09
    atsu
    0.09
    ui
    0.09
    left
    0.08
    hash
    0.08
    ysty
    0.08
    athi
    0.08
    ofte
    0.08
    Activations Density 0.001%

    No Known Activations