Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 98669
    Prev
    Next
    INDEX
    Explanations

    chord

    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
     lion
    -0.08
     Mimi
    -0.08
     tampon
    -0.08
     Lé
    -0.07
     Lind
    -0.07
     papa
    -0.07
    ongi
    -0.07
    lite
    -0.07
    kite
    -0.07
     achter
    -0.07
    POSITIVE LOGITS
     chords
    0.10
     riffs
    0.09
     murm
    0.08
     акор
    0.07
     rever
    0.07
     herz
    0.07
     developmental
    0.07
     बज
    0.07
     grp
    0.07
     بأن
    0.07
    Activations Density 0.003%

    No Known Activations