© 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. 805
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     att
    -0.08
     capable
    -0.07
    _C
    -0.07
     higher
    -0.07
    _interfaces
    -0.07
     probation
    -0.07
    iores
    -0.07
    "io
    -0.07
    Streams
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     musica
    0.08
    爷
    0.08
    bros
    0.08
    cripción
    0.08
    namen
    0.08
    куда
    0.08
    endon
    0.08
    kọ
    0.08
    chuhe
    0.08
    rẹ
    0.08
    Activations Density 0.000%

    No Known Activations