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. 103940
    Prev
    Next
    INDEX
    Explanations

    imaging or microscopy

    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
     strugg
    -0.09
     apost
    -0.09
     epo
    -0.08
     upkeep
    -0.08
     sinful
    -0.08
     accompagn
    -0.08
     marathon
    -0.08
     امر
    -0.08
     eun
    -0.08
     sanctuary
    -0.08
    POSITIVE LOGITS
     probing
    0.14
     probe
    0.13
     probes
    0.13
    Probe
    0.12
    _probe
    0.11
     Probe
    0.11
     interrog
    0.11
    Sensor
    0.11
     SENSOR
    0.10
    probe
    0.10
    Activations Density 0.010%

    No Known Activations