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. 120179
    Prev
    Next
    INDEX
    Explanations

    of

    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
    �
    -0.07
     ultra
    -0.07
    �
    -0.07
    б
    -0.07
    ам
    -0.07
    лении
    -0.07
     noc
    -0.07
     Mend
    -0.07
     plausible
    -0.07
     усп
    -0.07
    POSITIVE LOGITS
     beetje
    0.08
     hotspot
    0.08
    রের
    0.08
     ש
    0.07
     kie
    0.07
     uba
    0.07
     Metro
    0.07
     Keystone
    0.07
    wez
    0.07
    ર્સ
    0.07
    Activations Density 0.025%

    No Known Activations