© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45205
    Prev
    Next
    INDEX
    Explanations

    xy, yz planes

    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
    (serializers
    -0.08
     Warwick
    -0.08
    ein
    -0.08
     Homo
    -0.08
     Berliner
    -0.08
    融资
    -0.08
     accusations
    -0.08
     attacks
    -0.08
    eine
    -0.07
     نص
    -0.07
    POSITIVE LOGITS
     dimensional
    0.10
    -dimensional
    0.09
     dimension
    0.09
     plane
    0.08
    _dim
    0.08
    -plane
    0.08
     satisfactor
    0.08
    _plane
    0.08
     dimensions
    0.08
    _geo
    0.07
    Activations Density 0.002%

    No Known Activations