© 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. 49457
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    oblast
    -0.09
    ині
    -0.09
    ીને
    -0.09
     Schließlich
    -0.08
    ension
    -0.08
     scholar
    -0.08
     フ
    -0.08
    genoot
    -0.08
    ーぷん
    -0.08
     perio
    -0.08
    POSITIVE LOGITS
    ics
    0.15
    elateerde
    0.12
    ically
    0.11
    icas
    0.10
    osity
    0.10
    ování
    0.10
    ICS
    0.10
    átor
    0.10
    ické
    0.10
    ative
    0.09
    Activations Density 0.004%

    No Known Activations