© 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. 50426
    Prev
    Next
    INDEX
    Explanations

    cache

    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
     purchasing
    -0.08
    IENTATION
    -0.08
    орм
    -0.08
     cannabis
    -0.08
    ANCH
    -0.08
     cancers
    -0.08
    คาสิโน
    -0.08
     cancer
    -0.08
    agai
    -0.08
     Cancer
    -0.08
    POSITIVE LOGITS
     invalid
    0.15
     eviction
    0.14
    buster
    0.14
     misses
    0.14
    xia
    0.14
     miss
    0.13
    Invalid
    0.13
    able
    0.13
    _hit
    0.13
    -hit
    0.13
    Activations Density 0.008%

    No Known Activations