© 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. 617
    Prev
    Next
    INDEX
    Explanations

    television channels

    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
     remission
    -0.09
    .linalg
    -0.08
     powdered
    -0.08
     poisoned
    -0.08
    撞
    -0.08
    .calc
    -0.08
     repose
    -0.08
     immobil
    -0.08
     wounds
    -0.08
    liers
    -0.08
    POSITIVE LOGITS
    电视
    0.16
     방송
    0.15
     television
    0.14
     Broadcasting
    0.14
     broadcasters
    0.14
    节目
    0.14
     televis
    0.13
    テレビ
    0.13
     телевиз
    0.13
     televiz
    0.13
    Activations Density 0.043%

    No Known Activations