© 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. 11-RESID-POST-AA
    11. 95029
    Prev
    Next
    INDEX
    Explanations

    exploration and investigation

    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
     regeneration
    -0.08
     inspiring
    -0.08
     serenity
    -0.08
     escolher
    -0.08
     मात
    -0.07
     inspirational
    -0.07
     fortified
    -0.07
     intertwined
    -0.07
     inspiração
    -0.07
     muitas
    -0.07
    POSITIVE LOGITS
     probing
    0.14
     probes
    0.14
     experimenting
    0.14
    Probe
    0.13
     probe
    0.13
     Probe
    0.13
     ausprob
    0.13
    _probe
    0.13
    probe
    0.12
     эксперимент
    0.12
    Activations Density 0.054%

    No Known Activations