© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5741
    Prev
    Next
    INDEX
    Explanations

    perm

    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
    liz
    -0.09
    dua
    -0.09
    lers
    -0.08
    LOL
    -0.08
    axy
    -0.08
    drink
    -0.08
    icia
    -0.08
    ligini
    -0.08
    ić
    -0.08
    leyo
    -0.08
    POSITIVE LOGITS
    uting
    0.25
    ute
    0.24
    uted
    0.24
    utes
    0.22
    UTES
    0.17
    utate
    0.17
    UTE
    0.17
    ut
    0.16
    utions
    0.16
    uation
    0.16
    Activations Density 0.001%

    No Known Activations