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. 76920
    Prev
    Next
    INDEX
    Explanations

    Sentiment expression

    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
     faces
    -0.08
    pecies
    -0.08
    _submit
    -0.08
    Spo
    -0.07
    menes
    -0.07
    Submit
    -0.07
     MEN
    -0.07
    710
    -0.07
    spor
    -0.07
    707
    -0.07
    POSITIVE LOGITS
     epistem
    0.09
     hb
    0.09
     Ep
    0.08
    Ep
    0.08
     даму
    0.08
     breathed
    0.08
     happy
    0.07
     congratulations
    0.07
     happiness
    0.07
     jubil
    0.07
    Activations Density 1.812%

    No Known Activations