© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64686
    Prev
    Next
    INDEX
    Explanations

    arrows or direction

    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
     nuisance
    -0.09
     taxation
    -0.08
    dlg
    -0.08
     toutefois
    -0.07
    法人
    -0.07
     जुट
    -0.07
    lage
    -0.07
    jpeg
    -0.07
    exception
    -0.07
    Place
    -0.07
    POSITIVE LOGITS
     arrows
    0.16
    箭
    0.15
     arrow
    0.13
    (Direction
    0.13
     pointing
    0.12
     вниз
    0.12
    (direction
    0.12
    _arrow
    0.11
     omhoog
    0.11
     sideways
    0.11
    Activations Density 0.010%

    No Known Activations