© 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. 23-RESID-POST-AA
    11. 6089
    Prev
    Next
    INDEX
    Explanations

    keep

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tokony
    -0.10
     They'll
    -0.09
    ，他
    -0.09
    ，他们
    -0.09
     he'll
    -0.09
     they've
    -0.09
     如何
    -0.08
     Which
    -0.08
     tirelessly
    -0.08
     ...,
    -0.08
    POSITIVE LOGITS
     it
    0.18
     within
    0.15
     things
    0.14
    within
    0.14
    Within
    0.13
     consistent
    0.13
     language
    0.12
     focus
    0.12
     track
    0.12
     mindful
    0.11
    Activations Density 0.028%

    No Known Activations