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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102796
    Prev
    Next
    INDEX
    Explanations

    is

    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
    .only
    -0.10
     alleen
    -0.09
     sèlman
    -0.09
    _only
    -0.09
     slechts
    -0.09
    Only
    -0.09
     толькі
    -0.08
     only
    -0.08
     daadwerkelijk
    -0.08
     tikai
    -0.08
    POSITIVE LOGITS
     undefined
    0.19
     Undefined
    0.17
    undefined
    0.17
     unspecified
    0.15
    Undefined
    0.15
    (undefined
    0.14
     ???
    0.13
     something
    0.13
     NA
    0.12
     undef
    0.11
    Activations Density 0.018%

    No Known Activations