© 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. 48511
    Prev
    Next
    INDEX
    Explanations

    конт

    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
    od
    -0.10
    itte
    -0.08
    itiers
    -0.08
    IDs
    -0.08
    iti
    -0.08
    ouc
    -0.08
    étation
    -0.08
    itve
    -0.08
    οδο
    -0.07
    ogg
    -0.07
    POSITIVE LOGITS
    ൂർ
    0.12
    ூர்
    0.12
    ూర్
    0.11
    ૂર
    0.11
    акт
    0.11
    раст
    0.11
    ੂਰ
    0.11
    aktu
    0.10
    акте
    0.10
    ూరు
    0.10
    Activations Density 0.002%

    No Known Activations