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. 58399
    Prev
    Next
    INDEX
    Explanations

    induce

    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
     BUF
    -0.09
    chunks
    -0.09
     fread
    -0.08
    iface
    -0.08
    kring
    -0.08
    BUF
    -0.08
     fudge
    -0.08
     microphones
    -0.08
    _raw
    -0.08
     इस
    -0.07
    POSITIVE LOGITS
     apoptosis
    0.16
     apopt
    0.14
    .stop
    0.09
    -induced
    0.09
     হত্য
    0.09
     killing
    0.09
     останов
    0.08
     inhib
    0.08
    Stopping
    0.08
    -US
    0.08
    Activations Density 0.007%

    No Known Activations