© 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. 11-RESID-POST-AA
    11. 65515
    Prev
    Next
    INDEX
    Explanations

    to be/to do verbs

    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
    .toast
    -0.09
    .verbose
    -0.08
     volonté
    -0.07
     claire
    -0.07
     Gewalt
    -0.07
    .linear
    -0.07
     mort
    -0.07
     praised
    -0.07
     rec
    -0.07
    allage
    -0.07
    POSITIVE LOGITS
     మంది
    0.10
    ՞
    0.09
    ительных
    0.08
    (Create
    0.08
    Hvor
    0.08
     Cupid
    0.08
     ಬಾರಿ
    0.08
    acyj
    0.08
    _PWR
    0.08
    ünk
    0.08
    Activations Density 0.035%

    No Known Activations