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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50961
    Prev
    Next
    INDEX
    Explanations

    sheet pieces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ικούς
    -0.09
    .voice
    -0.09
    .line
    -0.09
     lijn
    -0.08
     dynasty
    -0.08
     bullets
    -0.08
    estrians
    -0.08
     आवाज
    -0.08
     Linie
    -0.08
     Stimme
    -0.08
    POSITIVE LOGITS
     sheet
    0.25
     sheets
    0.21
    _sheet
    0.21
     Sheet
    0.20
    (sheet
    0.20
     rectangular
    0.20
    sheet
    0.20
     panel
    0.19
    Sheet
    0.19
     morceau
    0.19
    Activations Density 0.126%

    No Known Activations