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. 67768
    Prev
    Next
    INDEX
    Explanations

    dump

    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
    �
    -0.08
    acter
    -0.08
    550
    -0.07
     Mes
    -0.07
    リング
    -0.07
    Determ
    -0.07
     Radar
    -0.07
     Webster
    -0.07
     rab
    -0.07
     Huck
    -0.07
    POSITIVE LOGITS
     clinker
    0.10
     dumping
    0.09
    cloth
    0.08
    Pile
    0.08
    izie
    0.08
     ashes
    0.08
    plass
    0.08
    pile
    0.08
     الطعام
    0.08
     lumps
    0.08
    Activations Density 0.006%

    No Known Activations