© 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. 48790
    Prev
    Next
    INDEX
    Explanations

    A

    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
    seg
    -0.11
    segment
    -0.09
    sex
    -0.08
    segu
    -0.08
    semantic
    -0.08
    prototype
    -0.08
     segment
    -0.08
    segments
    -0.08
    مش
    -0.08
    subs
    -0.08
    POSITIVE LOGITS
    ção
    0.11
    ÇO
    0.09
    ization
    0.09
    enzial
    0.09
    ÇÃO
    0.08
    eração
    0.08
    ções
    0.08
    ulation
    0.08
     레
    0.08
    eder
    0.08
    Activations Density 0.001%

    No Known Activations