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. 105982
    Prev
    Next
    INDEX
    Explanations

    Thoughts and misunderstandings

    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
     acompanhar
    -0.09
    iaj
    -0.08
    readonly
    -0.08
    apon
    -0.08
    model
    -0.08
     Aroma
    -0.08
    postos
    -0.08
    autore
    -0.08
     Excellence
    -0.08
     accompany
    -0.08
    POSITIVE LOGITS
     mistaken
    0.18
     mistakenly
    0.17
     misunderstanding
    0.17
     miscon
    0.17
    误
    0.15
     misunderstood
    0.14
     misunderstand
    0.14
     wrongly
    0.14
     confund
    0.14
     confused
    0.13
    Activations Density 0.072%

    No Known Activations