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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19052
    Prev
    Next
    INDEX
    Explanations

    film music composers

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jokes
    -0.08
     verbo
    -0.08
     lines
    -0.08
     vowels
    -0.08
    pivot
    -0.08
     rhyme
    -0.07
     texto
    -0.07
    .Line
    -0.07
    Gloss
    -0.07
     social
    -0.07
    POSITIVE LOGITS
     composers
    0.13
     composer
    0.13
     soundtrack
    0.12
     filmm
    0.12
     Composer
    0.11
     composing
    0.11
     kompon
    0.11
    Composer
    0.10
    	score
    0.10
    composer
    0.10
    Activations Density 0.016%

    No Known Activations