© 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. 23-RESID-POST-AA
    11. 96735
    Prev
    Next
    INDEX
    Explanations

    orientation

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keh
    -0.08
    ामा
    -0.08
     redevelopment
    -0.07
     tambah
    -0.07
    /Add
    -0.07
     Monaco
    -0.07
     terug
    -0.07
    म्प
    -0.07
     Addition
    -0.07
     واپس
    -0.07
    POSITIVE LOGITS
     orientation
    0.44
     orientations
    0.39
    Orientation
    0.39
     oriented
    0.38
    _orientation
    0.38
    orientation
    0.38
     Orientation
    0.38
    .orientation
    0.36
     orientación
    0.36
     orient
    0.35
    Activations Density 0.124%

    No Known Activations