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. 9221
    Prev
    Next
    INDEX
    Explanations

    realization

    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
    hede
    -0.08
     alkal
    -0.07
    kopf
    -0.07
     robbed
    -0.07
     Bumble
    -0.07
    thol
    -0.07
     Greenwood
    -0.07
    kampf
    -0.07
    �
    -0.07
    ाचार
    -0.07
    POSITIVE LOGITS
     concr
    0.08
     تحقق
    0.08
     pleinement
    0.08
     تو
    0.08
     religiosas
    0.07
    कर्ता
    0.07
    _DMA
    0.07
     conj
    0.07
     DM
    0.07
    滿
    0.07
    Activations Density 0.016%

    No Known Activations