© 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. 54588
    Prev
    Next
    INDEX
    Explanations

    years

    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
     divisible
    -0.08
    lox
    -0.08
     ij
    -0.08
    किन
    -0.08
    -0.08
    अर
    -0.07
     Kas
    -0.07
     n't
    -0.07
     nth
    -0.07
     सिंह
    -0.07
    POSITIVE LOGITS
    Early
    0.11
     shortly
    0.10
     early
    0.09
     frühen
    0.09
     frü
    0.09
    Late
    0.09
     temprano
    0.09
    early
    0.09
     совет
    0.09
     Early
    0.08
    Activations Density 0.058%
    No Known Activations