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. 43713
    Prev
    Next
    INDEX
    Explanations

    Soil sampling

    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
    connecting
    -0.08
    ountain
    -0.08
    onium
    -0.08
     konfer
    -0.08
     সাহায
    -0.08
     lasers
    -0.08
     connecting
    -0.08
    junction
    -0.08
     exot
    -0.08
     ভাব
    -0.08
    POSITIVE LOGITS
     Depth
    0.10
     profond
    0.10
    _DEPTH
    0.10
    _depth
    0.09
     depths
    0.09
     ರಿಂದ
    0.09
     depth
    0.09
     profondeur
    0.09
     profundidad
    0.09
    以内
    0.09
    Activations Density 0.006%

    No Known Activations