© 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. 103101
    Prev
    Next
    INDEX
    Explanations

    say "from"

    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
    iven
    -0.08
    فاعل
    -0.08
    -0.08
    1
    -0.08
     positive
    -0.07
     stronger
    -0.07
    فض
    -0.07
    -defined
    -0.07
    _structure
    -0.07
     (>
    -0.07
    POSITIVE LOGITS
     акы
    0.10
     entièrement
    0.09
     从
    0.09
     iš
    0.09
     тамам
    0.09
     começa
    0.09
     cag
    0.09
     börjar
    0.08
     começam
    0.08
    ҙән
    0.08
    Activations Density 0.003%
    No Known Activations