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. 48470
    Prev
    Next
    INDEX
    Explanations

    no

    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
     Latin
    -0.08
     verbs
    -0.08
     masa
    -0.08
     fuego
    -0.07
    verbs
    -0.07
    eban
    -0.07
     sleepy
    -0.07
     clon
    -0.07
     ഭാര
    -0.07
     bry
    -0.07
    POSITIVE LOGITS
     altogether
    0.09
    .ERROR
    0.09
    .Out
    0.08
     ühend
    0.08
    ,error
    0.08
     rejection
    0.08
    ūsu
    0.08
     вовсе
    0.08
    Nimbus
    0.08
     Unterneh
    0.08
    Activations Density 0.022%

    No Known Activations