© 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. 11-RESID-POST-AA
    11. 31141
    Prev
    Next
    INDEX
    Explanations

    surface analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emailing
    -0.09
    Email
    -0.08
     emails
    -0.08
    Lifetime
    -0.08
    (email
    -0.08
     uşa
    -0.08
    -email
    -0.07
    _email
    -0.07
    直营
    -0.07
     فروش
    -0.07
    POSITIVE LOGITS
     rugged
    0.14
    terrain
    0.13
     terrain
    0.13
    崎
    0.13
     protr
    0.12
     terrains
    0.12
     textured
    0.12
     uneven
    0.12
     Terrain
    0.12
     Gelände
    0.11
    Activations Density 0.049%

    No Known Activations