© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102890
    Prev
    Next
    INDEX
    Explanations

    Signal Modulation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bones
    -0.10
    _widget
    -0.10
     injuries
    -0.09
    _mentions
    -0.09
    _xpath
    -0.09
     inflam
    -0.09
    docker
    -0.09
     inflammatory
    -0.09
     prona
    -0.09
     Jardin
    -0.09
    POSITIVE LOGITS
     modulation
    0.23
     baud
    0.17
     multiplex
    0.17
     encoding
    0.17
     modem
    0.15
     carrier
    0.15
     Encoding
    0.15
     waveform
    0.15
     bandwidth
    0.15
     bitrate
    0.14
    Activations Density 0.017%

    No Known Activations