© 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 EvalsExportsAPI 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. 49354
    Prev
    Next
    INDEX
    Explanations

    Kn

    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
    સા
    -0.10
     kubwa
    -0.08
     მეტი
    -0.08
    isement
    -0.08
     Systeme
    -0.08
     discre
    -0.08
     તસ
    -0.08
     Usa
    -0.08
    usele
    -0.08
    itala
    -0.08
    POSITIVE LOGITS
    aves
    0.14
    ave
    0.13
    ights
    0.12
    IGHTS
    0.12
    AVE
    0.11
    AV
    0.11
    ighth
    0.10
    ighting
    0.10
    IGHT
    0.10
    ighter
    0.10
    Activations Density 0.001%

    No Known Activations