© 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. 129098
    Prev
    Next
    INDEX
    Explanations

    terminating decimals

    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
    manship
    -0.08
     proxim
    -0.08
     debut
    -0.08
     rally
    -0.07
    /items
    -0.07
     Chiefs
    -0.07
    第
    -0.07
     Jackets
    -0.07
    Grab
    -0.07
     melee
    -0.07
    POSITIVE LOGITS
     denomin
    0.10
     denominator
    0.10
    Exponent
    0.09
     знамен
    0.09
    альными
    0.09
    Arithmetic
    0.08
     основания
    0.08
     അനുവദ
    0.08
     sanitize
    0.08
     zend
    0.08
    Activations Density 0.027%

    No Known Activations