© 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. 47814
    Prev
    Next
    INDEX
    Explanations

    sp

    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
     vlie
    -0.09
     Inv
    -0.08
     Internal
    -0.08
    િવ
    -0.08
    _inv
    -0.07
     owning
    -0.07
     बैठे
    -0.07
     inv
    -0.07
     vliegtuig
    -0.07
     Lin
    -0.07
    POSITIVE LOGITS
    anned
    0.16
    anning
    0.12
    rawl
    0.11
     yc
    0.09
     브
    0.09
    'ét
    0.09
    änner
    0.08
    ans
    0.08
    raw
    0.08
    ੈਨ
    0.08
    Activations Density 0.001%

    No Known Activations