© 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. 102726
    Prev
    Next
    INDEX
    Explanations

    defining something

    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
     eigenlijk
    -0.10
     Relevant
    -0.09
     relevance
    -0.09
     vůbec
    -0.09
    Relevant
    -0.09
     기본
    -0.09
     בכלל
    -0.09
     Основ
    -0.09
     serieus
    -0.09
     Default
    -0.08
    POSITIVE LOGITS
     einzelne
    0.12
     tangible
    0.11
     einzelnen
    0.10
     konkre
    0.10
     plotted
    0.10
     einzel
    0.10
     mutum
    0.10
     konkrete
    0.09
     neatly
    0.09
     identifiable
    0.09
    Activations Density 0.028%

    No Known Activations