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. 8836
    Prev
    Next
    INDEX
    Explanations

    Hydroxide

    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
    措
    -0.08
    மை
    -0.08
     concession
    -0.08
    _vo
    -0.07
     shoreline
    -0.07
     reserver
    -0.07
     hinweg
    -0.07
    _SELECTION
    -0.07
     adopter
    -0.07
    blas
    -0.07
    POSITIVE LOGITS
    ikey
    0.09
    իկ
    0.08
     kho
    0.07
     دانلود
    0.07
    Paren
    0.07
     një
    0.07
     kosong
    0.07
     şekl
    0.07
    idia
    0.07
     gana
    0.07
    Activations Density 0.004%

    No Known Activations