© 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. 11-RESID-POST-AA
    11. 69667
    Prev
    Next
    INDEX
    Explanations

    mystery

    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
    форма
    -0.08
     corticost
    -0.07
    Uniform
    -0.07
    ло
    -0.07
    ngr
    -0.07
    potential
    -0.07
    FHIR
    -0.07
    ereich
    -0.07
    aged
    -0.07
     frequencies
    -0.07
    POSITIVE LOGITS
    -solving
    0.11
    谜
    0.10
    当天
    0.09
     mystery
    0.09
     murders
    0.08
     murder
    0.08
     Mystery
    0.08
     Murder
    0.08
     prins
    0.08
    现场
    0.08
    Activations Density 0.011%

    No Known Activations