© 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. 19-RESID-POST-AA
    11. 102372
    Prev
    Next
    INDEX
    Explanations

    remain

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iações
    -0.10
     deleting
    -0.10
     Removal
    -0.10
    ácie
    -0.10
    алі
    -0.09
     Removing
    -0.09
     Priority
    -0.09
     Азия
    -0.09
    azini
    -0.09
     prioridade
    -0.09
    POSITIVE LOGITS
     unused
    0.20
     untouched
    0.19
     un
    0.19
     una
    0.16
     untreated
    0.16
     unread
    0.16
     unm
    0.15
     und
    0.15
     une
    0.15
    unused
    0.14
    Activations Density 0.013%

    No Known Activations