© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5832
    Prev
    Next
    INDEX
    Explanations

    /G

    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
     പിട
    -0.07
    lookup
    -0.07
    nm
    -0.07
    ायी
    -0.07
    ನು
    -0.07
    त्ती
    -0.07
     تبلی
    -0.07
     kuiv
    -0.07
    ाइव
    -0.07
    Regex
    -0.07
    POSITIVE LOGITS
    he
    0.11
    it
    0.11
    ിറ്റ്
    0.10
    (it
    0.10
    err
    0.10
    itic
    0.10
    ిట్
    0.10
    itl
    0.10
    ogs
    0.10
    ists
    0.10
    Activations Density 0.001%

    No Known Activations