© 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. 29695
    Prev
    Next
    INDEX
    Explanations

    Natsuki in distress

    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
     эпох
    -0.09
     blended
    -0.09
     wilderness
    -0.08
     seguirá
    -0.08
    _bl
    -0.08
     оператор
    -0.08
     войны
    -0.08
     cleaned
    -0.08
    blij
    -0.08
     விச
    -0.07
    POSITIVE LOGITS
     symptoms
    0.11
     Symptoms
    0.11
    Symptoms
    0.11
     symptomen
    0.10
     Symptome
    0.09
     ciddi
    0.09
     allergic
    0.09
     síntomas
    0.09
     ailments
    0.09
     serious
    0.08
    Activations Density 0.027%

    No Known Activations