© 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. 102766
    Prev
    Next
    INDEX
    Explanations

    seeing

    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
     let's
    -0.11
     I've
    -0.09
     we're
    -0.09
     There's
    -0.09
     we
    -0.09
     Let's
    -0.09
     I'm
    -0.08
    I'm
    -0.08
    ిక
    -0.08
    hatikan
    -0.08
    POSITIVE LOGITS
    自己
    0.12
     firsthand
    0.12
     him
    0.12
     them
    0.11
     honom
    0.11
     כיצד
    0.11
     cómo
    0.10
     নিজ
    0.10
     kuidas
    0.10
     gebeuren
    0.10
    Activations Density 0.025%

    No Known Activations