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. 61100
    Prev
    Next
    INDEX
    Explanations

    checking problem statements

    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
     ray
    -0.07
     multic
    -0.07
     Cuisine
    -0.07
     Rental
    -0.07
    යේ
    -0.07
     rental
    -0.07
     пай
    -0.07
     {}↵↵
    -0.07
     wear
    -0.07
     plo
    -0.07
    POSITIVE LOGITS
    instead
    0.09
    urious
    0.09
    宜
    0.08
     исправ
    0.08
    orrect
    0.08
    alter
    0.08
    _MATCH
    0.08
     korr
    0.08
     instead
    0.08
     nhằm
    0.08
    Activations Density 0.027%

    No Known Activations