© 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. 7-RESID-POST-AA
    11. 1475
    Prev
    Next
    INDEX
    Explanations

    谱

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    فال
    -0.08
     Crew
    -0.08
    _staff
    -0.08
     фили
    -0.07
     adjunct
    -0.07
     SQLITE
    -0.07
     empire
    -0.07
     crystal
    -0.07
    Clinic
    -0.07
     Drew
    -0.07
    POSITIVE LOGITS
    Pv
    0.10
    涛
    0.09
     PSD
    0.09
     படம்
    0.08
     vsi
    0.08
     modi
    0.08
     patched
    0.08
     peaked
    0.08
     tilted
    0.08
     Tuna
    0.08
    Activations Density 0.003%

    No Known Activations