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. 101505
    Prev
    Next
    INDEX
    Explanations

    opposition

    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
     alvo
    -0.08
    iosa
    -0.08
    Entrada
    -0.08
    _INC
    -0.08
     Vict
    -0.08
    _ns
    -0.08
    พระ
    -0.08
    inue
    -0.07
    空
    -0.07
    _IO
    -0.07
    POSITIVE LOGITS
     opposing
    0.09
     begr
    0.08
     વચ્ચે
    0.08
     oppose
    0.08
    (str
    0.08
     Facing
    0.08
     layoffs
    0.07
     دنبال
    0.07
     друг
    0.07
     विरोध
    0.07
    Activations Density 0.002%

    No Known Activations