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. 108927
    Prev
    Next
    INDEX
    Explanations

    axis

    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
     dumpster
    -0.10
     Dumpster
    -0.09
    Dumpster
    -0.09
     Salon
    -0.08
    Crawler
    -0.08
     choir
    -0.08
    Hotel
    -0.07
    Salon
    -0.07
    Apartment
    -0.07
     coiff
    -0.07
    POSITIVE LOGITS
    .xlabel
    0.18
    _xlabel
    0.17
     xlabel
    0.17
    .ylabel
    0.16
    _ylabel
    0.16
    xlabel
    0.15
     axes
    0.15
    .axes
    0.14
     ylabel
    0.13
    Axes
    0.13
    Activations Density 0.006%

    No Known Activations