© 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. 23-RESID-POST-AA
    11. 47748
    Prev
    Next
    INDEX
    Explanations

    _A

    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
     Distributed
    -0.09
     Quality
    -0.08
     CT
    -0.08
     I
    -0.08
     Coinbase
    -0.08
    нання
    -0.08
    аның
    -0.08
     Crazy
    -0.08
     Mushroom
    -0.08
     السب
    -0.08
    POSITIVE LOGITS
    gent
    0.14
    uthor
    0.11
    fter
    0.11
    gency
    0.10
    _Name
    0.10
    ccess
    0.10
    _Type
    0.09
    oute
    0.09
    gon
    0.09
    _To
    0.09
    Activations Density 0.003%

    No Known Activations