© 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. 11-RESID-POST-AA
    11. 113232
    Prev
    Next
    INDEX
    Explanations

    algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     henkil
    -0.09
     oseb
    -0.09
     profesor
    -0.08
     person's
    -0.08
     feminine
    -0.08
    �
    -0.07
    PERSON
    -0.07
     vrouwelijke
    -0.07
     personal
    -0.07
    !"↵↵
    -0.07
    POSITIVE LOGITS
     contiguous
    0.13
     gaps
    0.11
     consecutive
    0.11
    连续
    0.10
    missing
    0.10
     coverage
    0.10
    coverage
    0.10
    gap
    0.10
     Coverage
    0.10
     Range
    0.10
    Activations Density 0.027%

    No Known Activations