© 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. 65601
    Prev
    Next
    INDEX
    Explanations

    uncertainty or being incorrect

    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
    _selector
    -0.08
    selector
    -0.07
    qua
    -0.07
     Kona
    -0.07
    legacy
    -0.07
    oor
    -0.07
    _predictions
    -0.07
     Jug
    -0.07
     Dubai
    -0.07
    _requests
    -0.07
    POSITIVE LOGITS
     unsure
    0.10
    Rw
    0.09
    .logic
    0.09
     optics
    0.09
     bisher
    0.09
     momentan
    0.08
     hoffe
    0.08
    GMT
    0.08
     keres
    0.08
     logic
    0.08
    Activations Density 0.083%

    No Known Activations