© 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. 254
    Prev
    Next
    INDEX
    Explanations

    less than or equal

    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
     avancer
    -0.08
     Spotify
    -0.08
    oglio
    -0.08
     måneder
    -0.08
     mitochond
    -0.08
     hefty
    -0.08
    �
    -0.08
     abase
    -0.08
     glo
    -0.08
    废
    -0.08
    POSITIVE LOGITS
    และ
    0.08
     lady
    0.08
     Lady
    0.08
    bounded
    0.08
    and
    0.08
     accommodate
    0.08
    but
    0.08
    lady
    0.08
    dropdown
    0.08
     accommodating
    0.08
    Activations Density 0.081%

    No Known Activations