© 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. 79385
    Prev
    Next
    INDEX
    Explanations

    instructional/technical documentation

    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
    自治
    -0.10
     anonymously
    -0.10
     구매
    -0.10
    绩
    -0.10
     ряд
    -0.10
     unopened
    -0.10
     achats
    -0.10
     instalações
    -0.10
    _xpath
    -0.10
     entrepreneurial
    -0.10
    POSITIVE LOGITS
     melodic
    0.12
     rhythmic
    0.12
     melodies
    0.11
     tones
    0.11
     tonal
    0.11
     riffs
    0.11
     melody
    0.11
     musical
    0.10
     rhythm
    0.10
     musicians
    0.10
    Activations Density 0.029%

    No Known Activations